Skip to main content
Glama

trident

by io.github.alexeibespalov
OverviewDiscussionsAdmin

add_container

Adds a new container (group/swimlane) to a live Trident document. Containers visually group related nodes. Use get_document_summary to check existing container IDs before adding to avoid duplicates. Requires a valid editor access token. To build an ERD (entity-relationship diagram), add one container per table with kind:"erd" and an x/y position, then add each field with add_node (container:, no x/y) — rows are stacked and the table sized automatically — and join TABLES (never rows) with add_connection using an ERD pair type such as "one_to_many".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tokenYesEditor access token for this document. The document ID is embedded in the token.
agentIdYesYOUR AI assistant name (e.g. "Claude.ai", "GitHub Copilot"). Shown as "[agentId] working with [userName]" in the collaboration presence dot.
userNameNoFirst name of the human you are assisting (ask them at session start if you do not know). Shown in the collaboration presence dot as "[agentId] working with [userName]".
containerYes
action_explanationNoOptional: brief explanation of what this action does and why (max 250 chars). Shown live to human collaborators in the AI cursor tooltip.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / container / properties / height
      Added value: +{
+  "description": "Optional: fixed height (use with width). Not for ERD tables. If you give a container a fixed size, make sure every node you add to it fits inside, or enlarge it with update_container.",
+  "type": "number"
+}
    • addedInput schema / properties / container / properties / kind
      Added value: +{
+  "description": "Optional: \"erd\" makes this container an ERD table (flat table: the label is the table name, child nodes are its field rows). Omit for a regular container.",
+  "enum": [
+    "erd"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / container / properties / width
      Added value: +{
+  "description": "Optional: fixed width. Omit width/height to let the container auto-size around its nodes. ERD tables default to 220; their height is managed automatically (28 header + 24 per row), so do not set it.",
+  "type": "number"
+}
    • changedInput schema / properties / container / properties / x / description
      Previous value: -"Optional: X position"New value: +"Optional: X position (required for kind:\"erd\" — the centre of the table)"
    • changedInput schema / properties / container / properties / y / description
      Previous value: -"Optional: Y position"New value: +"Optional: Y position (required for kind:\"erd\" — the centre of the table)"
  2. Changed1 schema field changed
    • addedInput schema / properties / container / properties / outlineColor
      Added value: +{
+  "description": "Optional: border/outline color (hex or color name), e.g. \"#5B7A99\" for a C4 system boundary.",
+  "type": "string"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false. The description adds real context beyond that: it requires a valid editor access token, warns about duplicate IDs, and explains auto-sizing behavior (rows stacked, table sized automatically, ERD height managed). It does not describe the response payload, but annotations carry the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and duplicate-check guidance are front-loaded, but the trailing ERD tutorial is long and spans several sibling tools, making the definition read partly like workflow documentation rather than this tool's contract. It earns its place but is heavier than needed for a single call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested-object, 5-parameter mutation tool with no output schema, the description covers auth, duplicate risk, sizing behavior, and the surrounding workflow well. Remaining gap is the return value/shape, which is minor given no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80% so the baseline is 3, but the description adds interaction semantics the schema cannot express: kind:"erd" requires x/y (table centre), rows are passed via add_node with container:<table id> and no x/y, and ERD height must not be set. That meaningfully exceeds the schema's per-field prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ("Adds a new container (group/swimlane)") and immediately defines what a container is, distinguishing it from add_node/add_connection by scope. An agent can tell this creates grouping structures rather than content nodes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names get_document_summary as the prerequisite check to avoid duplicate IDs, and lays out the full multi-tool ERD workflow (add one container per table, then add_node rows, then add_connection between tables). It states both when to use it and which sibling tools to sequence with it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All trident toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources